A navigation system for an underwater vehicle using a self-organizing map

Underwater vehicles are expected as attractive tools in the deep ocean. In order to realize useful and practical robots, underwater vehicles should take their action by judging the changing condition from their own sensors and actuators, and are desirable to make their behavior, because of features caused by the working environment. Development of navigation system, which can navigate vehicles without the collision to the obstacle, is one of the most important problems. Self-Organizing Map (SOM) is applied to robot's system, because of the capability of clustering and feature extraction. The efficiency of the system is investigated through simulations and experiments with an underwater vehicle "Twin-Burger". Copyright (C) 2003 IFAC.